{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5655730962753296, "min": 1.5456167459487915, "max": 1.8768645524978638, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31461.7578125, "min": 27528.861328125, "max": 39196.15625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 45.93396226415094, "min": 37.76335877862596, "max": 71.3768115942029, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19476.0, "min": 18652.0, "max": 20572.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1582.8987936518504, "min": 1524.5667595307027, "max": 1599.3235310918258, "count": 500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 335574.54425419227, "min": 214114.53255754447, "max": 401846.2350204096, "count": 500 }, "SoccerTwos.Step.mean": { "value": 9999992.0, "min": 5009998.0, "max": 9999992.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 9999992.0, "min": 5009998.0, "max": 9999992.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.03813937306404114, "min": -0.1265849769115448, "max": 0.09336826205253601, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.08554744720459, "min": -22.911880493164062, "max": 19.98080825805664, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03269457072019577, "min": -0.12756845355033875, "max": 0.09128137677907944, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.931248664855957, "min": -23.535907745361328, "max": 19.53421401977539, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.1358867917420729, "min": -0.406139039738293, "max": 0.2910804472156077, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -28.807999849319458, "min": -75.94800043106079, "max": 58.09199994802475, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.1358867917420729, "min": -0.406139039738293, "max": 0.2910804472156077, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -28.807999849319458, "min": -75.94800043106079, "max": 58.09199994802475, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017273846360816, "min": 0.009380777090458044, "max": 0.023266254582752784, "count": 243 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017273846360816, "min": 0.009380777090458044, "max": 0.023266254582752784, "count": 243 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1211458203693231, "min": 0.09803028305371603, "max": 0.13208639870087305, "count": 243 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1211458203693231, "min": 0.09803028305371603, "max": 0.13208639870087305, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12324821750322977, "min": 0.09940491616725922, "max": 0.13452429076035818, "count": 243 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12324821750322977, "min": 0.09940491616725922, "max": 0.13452429076035818, "count": 243 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 243 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 243 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 243 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 243 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 243 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 243 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693498281", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\frede\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1", "numpy_version": "1.25.2", "end_time_seconds": "1693520998" }, "total": 22717.084853199998, "count": 1, "self": 0.8225978999980725, "children": { "run_training.setup": { "total": 0.11150899999999986, "count": 1, "self": 0.11150899999999986 }, "TrainerController.start_learning": { "total": 22716.1507463, "count": 1, "self": 13.733896200734307, "children": { "TrainerController._reset_env": { "total": 5.1019690999999066, "count": 26, "self": 5.1019690999999066 }, "TrainerController.advance": { "total": 22697.11072609927, "count": 351732, "self": 14.132402697363432, "children": { "env_step": { "total": 9695.224640900826, "count": 351732, "self": 7646.071231402144, "children": { "SubprocessEnvManager._take_step": { "total": 2041.2051140997442, "count": 351732, "self": 72.88704509946706, "children": { "TorchPolicy.evaluate": { "total": 1968.318069000277, "count": 626724, "self": 1968.318069000277 } } }, "workers": { "total": 7.948295398937329, "count": 351732, "self": 0.0, "children": { "worker_root": { "total": 22691.773680901515, "count": 351732, "is_parallel": true, "self": 16514.399365101664, "children": { "steps_from_proto": { "total": 0.08334620000222337, "count": 52, "is_parallel": true, "self": 0.0162021999989701, "children": { "_process_rank_one_or_two_observation": { "total": 0.06714400000325327, "count": 208, "is_parallel": true, "self": 0.06714400000325327 } } }, "UnityEnvironment.step": { "total": 6177.290969599848, "count": 351732, "is_parallel": true, "self": 334.08008729807807, "children": { "UnityEnvironment._generate_step_input": { "total": 258.90624560145477, "count": 351732, "is_parallel": true, "self": 258.90624560145477 }, "communicator.exchange": { "total": 4534.654680201005, "count": 351732, "is_parallel": true, "self": 4534.654680201005 }, "steps_from_proto": { "total": 1049.6499564993096, "count": 703464, "is_parallel": true, "self": 201.5530024998725, "children": { "_process_rank_one_or_two_observation": { "total": 848.0969539994371, "count": 2813856, "is_parallel": true, "self": 848.0969539994371 } } } } } } } } } } }, "trainer_advance": { "total": 12987.753682501077, "count": 351732, "self": 81.42977380084085, "children": { "process_trajectory": { "total": 2537.4829985002407, "count": 351732, "self": 2535.0490125002448, "children": { "RLTrainer._checkpoint": { "total": 2.4339859999959117, "count": 10, "self": 2.4339859999959117 } } }, "_update_policy": { "total": 10368.840910199995, "count": 243, "self": 931.5842583999856, "children": { "TorchPOCAOptimizer.update": { "total": 9437.25665180001, "count": 7290, "self": 9437.25665180001 } } } } } } }, "trainer_threads": { "total": 1.1000010999850929e-06, "count": 1, "self": 1.1000010999850929e-06 }, "TrainerController._save_models": { "total": 0.20415379999758443, "count": 1, "self": 0.003443899997364497, "children": { "RLTrainer._checkpoint": { "total": 0.20070990000021993, "count": 1, "self": 0.20070990000021993 } } } } } } }